Observatoire des droits humains (anglais seulement)

OpenAI’s models autonomously hacked a tech startup. It signals a seismic shift in cybersecurity

(Version anglaise seulement)

par Hussein Abbass, Professor, School of Systems and Computing, UNSW

An autonomous agent powered by OpenAI’s advanced artificial intelligence (AI) models went rogue during a security test and hacked multi-billion dollar tech startup, Hugging Face, last week.

The agent didn’t just exploit vulnerabilities in Hugging Face’s systems to achieve what it perceived as a strategic gain. It also exploited vulnerabilities within OpenAI’s infrastructure.

Of course, hacks are very common cyber threats that organisations face frequently. But this incident is different, because the AI agent acted without any human input. It signals a seismic shift in…

Lire l'article complet